## What changed
Tag `codex.tools.incremental_updates` counters with the qualified tool name alongside the action. Continue excluding initial catalogs and namespace headers, while counting each removed namespace member.
Add `codex.tools.spec_description_bytes` to measure UTF-8 description bytes when an existing tool definition is replaced. Skip definitions without descriptions and use logarithmic histogram boundaries up to 1 MiB.
## Testing
Extend namespace transition tests to check per-tool counts and description sizes. Add scenario assertions for replacement metrics with incremental tool updates and their absence on the non-incremental request path.
GitOrigin-RevId: e20e6d81f21a867b285df1f0da005c2806dd03c6
## Why
With granular sandbox approvals disabled, `write_stdin` rejected input to terminals retaining additional permissions even when those permissions were still granted.
## What changed
Let input reach approval review when the terminal's retained permissions match active grants for its environment. Require identical filesystem grants, including entry order, and an active network grant when retained permissions enable network access. Each input still requires review.
Keep rejecting input when retained authority is no longer covered or the approval policy changes to `Never`.
## Testing
Add regression coverage for user and Guardian review, turn grant expiry, session grants, and switching to `Never`. Cover filesystem restrictions, protected metadata, symlinks, and ordered denials, and verify that rejected input never reaches the terminal.
GitOrigin-RevId: 9abf7da8d03b1526d26ca2a718e36349a255330b
## Why
Terminal status previously collapsed completed and failed turns into `idle` and reported blocking prompts without a reason. Blocking detection also depended on terminal title settings.
## What changed
- Emit `done` and `error` through OSC 7501 for live turn results, retaining them until deliberate keyboard, paste, or mouse input acknowledges them. Mouse movement does not acknowledge results.
- Classify blocking requests with `kind=permission`, `kind=question`, or `kind=auth`, including requests hidden behind another view or delayed while typing, independently of terminal title settings.
- Keep pending follow-up work and active goals `working`. Treat interrupted turns and replayed results as `idle` rather than new results.
- Preserve the existing iTerm2 OSC 21337 labels and indicators, mapping `done` and `error` to `Idle`.
## Testing
Add lifecycle and input-acknowledgment tests covering approvals, completion, failure, interruption, replay, pending follow-ups, and active goals. Extend blocking-request assertions and terminal protocol snapshots for the new states and reasons.
GitOrigin-RevId: 90bad1d54d8b3b9e3cec66fbd3bf3df0c42b995b
## What changed
Use the stable and experimental bundles generated by `//bazel/schema:app-server` as compile-time inputs for `app-server-protocol` instead of the checked-in bundles.
Generalize `schema_generator_sources` to `schema_sources` so it can stage Rust sources alongside generated bundles. Keep empty bundle placeholders for the on-demand schema generator, which derives its output from Rust sources.
GitOrigin-RevId: a976c420a3698d631f3ea7c698b15b82391158e5
## What changed
Wait for the subprocess readiness marker before cancelling in
`process_exec_tool_call_cancellation_allows_sigterm_cleanup`, removing the
one-second polling cutoff. Poll readiness alongside execution under the existing
five-second timeout, then cancel and await execution if that timeout expires so
cleanup completes before the test fails.
GitOrigin-RevId: ba47dad9ba87fb5dc3bd087380811655387f825a
## Why
Environment tool availability and selectors should remain stable as selected environments become ready.
## What changed
- Keep configured environment tools advertised even when no execution environment is ready, and derive `environment_id` selectors from all selected environments.
- Return guidance to wait when an environment is unavailable, while preserving errors for unknown environment IDs. Require a usable primary environment for `write_stdin`.
- Always include `shell` and `login` in the `exec_command` schema and mark `stable_environment_tools` as removed.
## Testing
Update integration tests to expect environment tools with empty or starting environments, and remove explicit feature opt-ins from affected scenarios.
GitOrigin-RevId: 1590c1b5be16a39e4a370663c552b881602545b5
## What changed
Emit the Daybreak notice after replacing or removing the placeholder session header so the notice follows the configured header.
## Testing
Extend the resumed-history snapshot test to start with a placeholder header and verify the full transcript order: session header, Daybreak notice, and replayed user and assistant messages.
GitOrigin-RevId: 536f717b2859d2fe319756f52123b4cd0407cb66
## What changed
- Add `//bazel/schema:app-server` to generate stable and experimental schemas from Rust sources without depending on committed precomputed bundles.
- Add `//sdk/python:generated` to generate Python SDK models, the notification registry, and API methods from the stable schema in scratch space, using dependencies from `uv.lock`.
- Add `generate-types --no-format` to skip formatters for build outputs while preserving formatting by default.
## Testing
Extend contract generation tests to regenerate in a temporary SDK copy, checking byte equality for formatted output and AST equality for unformatted output.
GitOrigin-RevId: 9ca7daa8ac0a33c4106a9e95c2f48bbded07df21
## Why
MCP request failures and tool errors reported only through `codex/telemetry` metadata previously received an `unknown` error code, obscuring the failure category.
## What changed
- Classify typed request failures into bounded codes such as `request_timeout`, `transport_closed`, and `protocol_error`, and carry them into MCP call metrics and spans before errors become strings.
- Preserve typed timeouts when a prepared tool call exhausts its deadline during trusted access lookup.
- Accept allowlisted `error_code` values from `codex/telemetry` as a fallback after structured content and connector authentication metadata. Keep model output unchanged and ignore unrecognized metadata codes.
## Testing
Add coverage for typed errors wrapped in context, prepared-call timeout classification, metadata precedence and rejection, unchanged model output, and exported span error attributes.
GitOrigin-RevId: d7a440a6c9119b8a07a7f1fad697eb25af506f00
## What changed
- Upgrade `rules_python` from 1.7.0 to 2.4.2 and update `MODULE.bazel.lock`.
- Enable `--windows_enable_symlinks` in `.bazelrc`, as `rules_python` 2.x requires symlink support for Windows Python launchers.
GitOrigin-RevId: 303da258c74b18d0d0df8d4eebb830c57f14cca4
## Why
Advancing the test clock expires the review, but command cancellation and output drainage still run asynchronously. The model can poll before the final timeout failure is available.
## What changed
Hold the initial tool result until the command emits `ExecCommandEnd`, with a bounded wait that also catches unexpected approval requests or turn completion. Only request a poll when the initial result reports a running process, and accept the timeout output from either `exec_command` or `write_stdin`.
Keep the assertions that the model receives the timeout explanation without a user approval prompt or a misleading user-rejection message.
GitOrigin-RevId: 219a1579dce35caf8f0d45b1d92a7343ec1a8935
## What changed
Add `ListKeymap::vertical_action_for` and `ScrollState::apply_vertical_action` to share key resolution, selection movement, and visibility handling across the experimental features, hooks, memories, skills, and multi-select views. Preserve navigation priority, search input handling, and item reordering precedence.
## Testing
Update scroll-state tests to exercise the shared action handler and picker tests to navigate through key events. Cover overlapping page-down and move-left bindings when item reordering is disabled.
GitOrigin-RevId: 29927b0a4de0fbeb4c0dd19c418b8f60fffb8a7d
## Why
Coordinated MCP OAuth refresh must stop retrying a definitively rejected refresh token, including after the runtime is rebuilt.
## What changed
Remove the rejected refresh token while preserving the access token and credential record. Compare stored credentials under the appropriate locks before writing so a replacement login is preserved, and update file entries using their existing keys.
Keep rejection handling alive through caller cancellation and prevent reuse within the runtime even if persistence fails. For ordinary direct-keyring credentials shared across `CODEX_HOME` directories, retire the token only in the current runtime because locking does not span those directories. Report persistence failures without exposing backend diagnostics.
## Testing
Add coverage for reauthentication after runtime rebuild, legacy file keys, cancellation with a concurrent credential replacement, keyring scope, and persistence failures with diagnostic redaction.
GitOrigin-RevId: a6e602ca2e2893ed711d853becc45142d9575fab
## Why
PowerShell safety checks can mistake a literal `start` argument for a URL-launch command, or combine a process launch with a URL from a separate command.
## What changed
Classify independently parsed literal PowerShell commands separately so commands such as `Write-Output start 'https://example.com'` do not trigger URL-launch checks. Retain conservative checks for pipelines, script state, executable strings, and shell or terminal wrappers, while continuing to detect actual URL launches and destructive commands.
## Testing
Add policy regression coverage for literal arguments, separate commands, URL launches, wrappers, and destructive commands, plus a Windows integration test covering execution and policy rejection.
GitOrigin-RevId: 2878aa86bc36b44c60230cc1de3430922b28b81a
## What changed
Rename the grant manager and supporting modules in `codex-rs/login` to expose `OAuthSessionManager`, its configuration and status types, `OAuthLoginControl`, and `subscribe_oauth_session_status`.
Keep the existing gateway API names as compatibility aliases and retain the credential storage paths and namespace so saved credentials remain usable. Update the existing authentication tests to use the OAuth session API.
GitOrigin-RevId: 72cea12be606dde28cf42809e7f8b8807cbc4a2a
## Why
Remote MCP environment filtering could drop `SystemDrive` and `LocalAppData`. Explicit overrides also need Windows-aware merging to replace inherited variables with differently cased names.
## What changed
- Preserve `SYSTEMDRIVE` and `LOCALAPPDATA` when remote environment variables activate the allowlist.
- Apply explicit environment overrides through the executor environment policy, while retaining the final overlay for variables excluded by the allowlist.
## Testing
Extend environment-policy tests to cover the additional Windows variables, overrides with differently cased names, and the final overlay used by older executors.
GitOrigin-RevId: 36df69117f248536e47cf7e1d855b99a138fe698
## Why
Unarchiving a thread previously read rollout metadata across both active and archived history, including unrelated threads.
## What changed
Use `RolloutReferenceIndex::scan_archived_threads` to restrict discovery to archived files whose canonical filenames match the requested thread. Continue validating ownership through session metadata and include compressed and reverted rollouts.
## Testing
Add coverage for compressed and replacement archived rollouts, metadata ownership mismatches, unrelated filenames, and exclusion of active rollouts.
GitOrigin-RevId: 8784f3502b839dcb4a3839744010e350d0196545
## Why
Thread stores need a way to reuse history and writer state loaded while preparing a resume, rather than loading them again during session startup.
## What changed
- Add an opaque, single-use `ThreadStoreResumePreparation` and an optional preparation in `StartThreadOptions`.
- Pass preparation through session startup to `ThreadStore::resume_thread_with_preparation`, which defaults to an unsupported-operation error.
- Reject preparation for ephemeral threads or threads without resumed history. Continue using `resume_thread` when no preparation is supplied.
## Testing
Add a regression test verifying that supplied preparation selects the prepared store path and propagates its unsupported-operation error instead of falling back to ordinary resume.
GitOrigin-RevId: 26537d9b83443bd56341d6afc713f32b999dc67c
## Why
Native extensions need configured Responses metadata for request attribution, but extension calls used the MCP metadata template, which omits it. Image requests also did not forward the turn metadata to the backend.
## What changed
Use the Responses metadata template for native extension calls while continuing to exclude tool inventory. Forward the resulting metadata in the `x-codex-turn-metadata` header on image generation and edit requests.
## Testing
Extend metadata tests to cover configured values in extension calls and app-server tests to verify `display_name` and `turn_trigger` on image generation and edit requests, including a Unicode display name.
GitOrigin-RevId: a2ffaa4d15259c662917612391b8717ee34b9c6c
## Why
Unsupported evidence currently shares a single Decisions comparison reason, making it difficult to distinguish why a comparison was skipped.
## What changed
Report separate reasons for unsupported developer messages, other non-user messages, trusted skills, images, and audio. Keep these outcomes classified as `skipped` and retain the generic reason for other unsupported evidence. Expose `TrustedSkills::KIND` for identifying trusted skill fragments.
## Testing
Expand adapter tests for the distinct rejection reasons and add a lifecycle case verifying that trusted skill evidence skips the Decisions request, reports `trusted_skills`, and preserves the baseline score.
GitOrigin-RevId: 98f076d1aa6771d0209e7f5910eed0dcc40c6263
## Why
Concurrent TLS client builds can independently load the same platform trust store. Share overlapping loads while preserving fresh trust reads for later builds.
## What changed
- Share one in-flight native root load without reusing completed loads.
- Bypass sharing when `SSL_CERT_FILE` or `SSL_CERT_DIR` is set, and continue reading custom CA bundles independently for every build.
## Testing
Add tests for overlapping loads, fresh trust after completion, and recovery from a panicking loader. Extend TLS handshake coverage to verify that replacing a custom CA file affects new configurations while existing configurations retain their trust, and that empty or removed files produce errors.
GitOrigin-RevId: 1465ef3faf82f53651d9dbfe314341b17346580b
## Why
Clients need a way to update individual turn metadata entries without replacing the existing client metadata map.
## What changed
Add the experimental `responsesapiClientMetadataPatch` field to `turn/start` and `turn/steer`. Patches add or overwrite entries while retaining other keys and apply after `responsesapiClientMetadata` when both are supplied. The existing field retains replacement semantics, including clearing unprotected entries with an empty map.
Continue protecting reserved metadata keys and preserving targeted `misalignment_override` continuations across updates.
## Testing
Extend the app-server metadata integration test to cover replacement and patch steering, patch precedence at turn start, preservation of unrelated entries during patches, and protection of targeted continuations.
GitOrigin-RevId: 8c4da3ba1b87329da20b5295846bdcf3a88126de
## Why
A queued skill refresh can outlive the workspace it was requested for when the working directory changes.
## What changed
- Refresh skills for the current working directory when the skills management popup closes.
- Ignore queued `ListSkills` commands whose directories do not include the current working directory.
- Require an explicit working directory when constructing `WorkspaceCommand` and always pass it to app-server command execution. Update Git and GitHub metadata probes to use the constructor.
## Testing
Extend regression tests to verify that closing skill management refreshes the configured working directory and that stale skill refreshes after a directory change do not issue a `skills/list` request.
GitOrigin-RevId: 47ad1d95930840b3f6f0e20d7d8fe8d025e789e6
## Why
The Agent Command Center does not open a workspace, so viewing it should not require consent for the launch directory.
## What changed
Skip startup folder consent when opening the agents overview, while preserving initialization for the embedded fallback. Check folder trust before starting the first task, including through `/new` after dismissing the overview. On Windows, retain the sandbox setup prompt after folder trust is granted.
## Testing
Add CLI tests for starting a task from an untrusted folder through the overview and through `/new` after dismissing it. A terminal snapshot verifies that the overview appears before folder consent.
GitOrigin-RevId: 129be14a354b8abde2e8430c81599e2064ccac87
## Why
Replaying an in-progress turn reset the TUI's `Working` timer to zero, hiding time already spent on the turn.
## What changed
Initialize the status timer from the turn's `started_at` timestamp when replaying turns or turn-start notifications. Keep the zero-time fallback when the timestamp is missing, and clamp future timestamps to zero elapsed time.
## Testing
Extend history replay tests to verify elapsed time for both thread snapshots and replayed in-progress turns, and normalize the timer in rendering snapshots.
GitOrigin-RevId: 36a48f43d0d7aa530f1bfe6dbefa9f0885cbd6c7
## What changed
- Preserve approval resolution sources through tool errors and tag cancelled MCP approvals with `error_type=approval`, `error_code=cancelled`, and `approval_source` (`guardian`, `user`, `hook`, or `unknown`). The source identifies the reviewer, not who caused cancellation.
- Record `context_changed` when validating a Guardian allow against changed authorization or review context, even when a concurrent stop or history reset determines the outcome. Retain the flag across retries and fresh-checkpoint recovery, and include it in the Guardian review counter.
GitOrigin-RevId: a19a986a7565f9a78a9bb2eaabdb5651834d28b8
## Why
Loading older history could place transcript entries before the `Thread forked from` notice, separating fork lineage from the session header.
## What changed
Treat fork lineage as a session prefix in both the TUI transcript and transcript overlay so older pages are inserted after it.
## Testing
Add regression tests for repeated history prepends in both paths, verifying that fork lineage stays first.
GitOrigin-RevId: 71497fb7ffa992c72ee08617d318aa3119e71275
## Why
An asynchronous approval currently waits for the redundant synchronous review to finish cancellation cleanup before returning a decision.
## What changed
Cancel the redundant review and let it drain under the parent's `ReviewerTasks` tracker so a current approval can return immediately. Revalidate the approval and check cancellation before approving the action. Hosts without a task tracker continue to wait for cleanup.
Keep the reviewer reservation held until cleanup completes, and let shutdown join the tracked attempt. Discard late results and evidence from the cancelled review.
## Testing
Add tests covering current, invalidated, and cancelled approvals while cleanup is blocked, suppression of late evidence, reviewer reservations during cleanup, and shutdown waiting for abandoned attempts.
GitOrigin-RevId: f227738e545243f99c19a6c557a78d330f9d2767
## What changed
Increase memory extension resource retention from 7 to 14 days before pruning.
## Testing
Update pruning and startup test fixtures for the 14-day retention window, including resources at the exact cutoff.
GitOrigin-RevId: 5044a1262c8806245d90d567cd84b21aa0d3da43
## Why
Collecting a diff previously launched a Git process for every untracked file at once, allowing process counts to grow with the number of files.
## What changed
Limit untracked-file diffs to eight concurrent operations per collection while preserving patch order and skipping failed file diffs. Concurrent collections each retain their own limit.
## Testing
Add tests for independent concurrency limits, failed-file handling, and patch order and application with tracked changes, binary files, and filenames containing spaces or a leading dash.
GitOrigin-RevId: 896e896eae62ba9b7acf3e8946c235fe725ced40
## Why
Windows MXC needs valid host startup variables, while an empty child environment must remain empty for the SDK to select Windows user-profile defaults.
## What changed
- Replace caller overrides of `SystemDrive` and `LOCALAPPDATA` case-insensitively with nonempty Unicode host values, failing before launch if either is unavailable.
- Track whether the original child environment was empty, ignoring launcher transport keys. Supply host `SystemRoot` for launcher bootstrap in that case, then clear the bootstrap environment before the SDK selects defaults.
## Testing
Extend transport tests to cover host-value replacement and preservation of empty child environments. Strengthen the PowerShell fallback RPC test to require `SystemDrive`, `LOCALAPPDATA`, `USERPROFILE`, and `PATH` in the child.
GitOrigin-RevId: a097e1079069ef897ebb5ba5e63546328c5faeaa
## Why
Compression replaces `.jsonl` rollout files with `.jsonl.zst` files, so checking only the original path can skip existing sessions. Compression can also replace a file between path lookup and canonicalization.
## What changed
- Resolve compressed rollout alternatives when selecting the latest local session.
- Retry rollout path resolution when files disappear during lookup or canonicalization.
## Testing
Extend coverage to verify latest-session filtering after startup compression and resuming a compressed rollout through its original relative `.jsonl` path with preserved turns.
GitOrigin-RevId: a4d5c399567ab4c7cd8aaa8b5f38821ee8b8d802
## Why
Doctor's rollout statistics only counted `.jsonl` files, omitting storage used by compressed `.jsonl.zst` rollouts.
## What changed
Recognize compressed rollouts when collecting active and archived file counts, total bytes, and average bytes. Count both physical files when plain and compressed representations coexist, while continuing to ignore unrelated files and compression temporary files.
## Testing
Extend the rollout statistics test to cover nested plain and compressed files, coexisting representations, archived compressed rollouts, and ignored files, with a snapshot of the reported counts and sizes.
GitOrigin-RevId: 46197f9741884668b50fb6a1d0a07060020f12ed
## Why
Filesystem lookups by thread or rollout ID check whether unrelated compressed rollouts have an uncompressed sibling. These checks are unnecessary when the filename does not match the requested ID.
## What changed
Apply the thread or rollout ID filter before resolving plain/compressed file precedence. Preserve preference for uncompressed files and selection of the newest rollout for a thread.
## Testing
Extend lookup tests to cover unrelated compressed files, uncompressed-file precedence, missing rollout IDs, and rollout ID tie-breaking for files with the same timestamp.
GitOrigin-RevId: 5bdb56ebec8031fceb5f6adbfcf644ad010e52f2
## What changed
Include a `refresh_reason` diagnostic in ChatGPT OAuth token refresh requests to distinguish `proactive_expiry`, `scheduled`, `unauthorized_recovery`, and `forced` refreshes. Omit the field for gateway refresh requests.
## Testing
Extend refresh tests to check the reported reasons, including scheduled refreshes when access token expiry is unavailable.
GitOrigin-RevId: b0294a61ffc3089a66e7b132d4f45661a9e18d38
## Why
A remote primary environment could supply its working directory and workspace roots to host plugins and MCP processes, breaking relative MCP executable resolution and applying the wrong workspace permissions.
## What changed
- Build host configuration from the local environment, falling back to the session's host working directory and runtime workspace roots when no local environment is selected. Preserve explicitly empty local roots.
- Use the same host configuration for MCP startup and refresh, and refresh MCP state when runtime workspace roots change.
- Keep repository skill discovery paired with the primary executor's working directory and filesystem.
- Box skill warmup and turn context construction futures to reduce enclosing future sizes.
## Testing
Extend the MCP integration test to cover a remote primary with populated, empty, or absent local roots; relative executable resolution before and after refresh; workspace-root revocation; and remote repository skill discovery.
GitOrigin-RevId: 21a73c90507b55fd94261e7bf348695ff8466a24
## Why
Stale authorization requires refreshing local evidence, so service retry backoff unnecessarily delays the next review attempt.
## What changed
Yield cooperatively before retrying `StaleAuthorization`, then check cancellation and the shared deadline. Keep retries within the existing attempt budget.
## Testing
Extend paused-time tests to cover recovery with fresh evidence and exhaustion of the shared attempt budget, asserting that retries incur no backoff and return the final attempt's evidence.
GitOrigin-RevId: fda7ddd040a761d08883740bb5e7aaecacfa6091
## Why
PTY reads can split a redraw while the reconnect notice is temporarily erased. The test can then submit `/status` before reconnection finishes, when Enter is suppressed.
## What changed
Make the `discovered` daemon startup test inspect only completed synchronized terminal updates. Type `/status` separately from Enter and wait for its command popup before submitting. Gate both inputs on a replacement daemon PID and the absence of the reconnect notice.
GitOrigin-RevId: a99af0f26753d81458dbce2c30ecc120ff78d3f4
Extend phase-one request tests for both memory versions with reasoning,
developer messages, and assistant ciphertext whose combined size exceeds
the reader budget while individual records remain below the record limit.
Verify that earlier extraction evidence and assistant text alongside large
ciphertext remain in the request, with `encrypted_content` excluded.
GitOrigin-RevId: f0e85e368e5a94d491d0aa4ae1688f47d873ccd9
## Why
Blocking rollout reads can continue decompressing and scanning history after the calling async task is dropped.
## What changed
Propagate caller cancellation through rollout readers, prefix validation, model-context scans, history materialization, and working-directory lookup. Check cancellation during compressed input and output, bounded reads, seeks, and between history records. Return an error on cancellation so partial history cannot be mistaken for a complete read.
## Testing
Add regression coverage for dropping a caller during decompression, cancelling compressed input and output (including skippable frames), cancelling reads and seeks on plain and decoded snapshots, and cancelling history materialization between records.
GitOrigin-RevId: e3dac952789b53402f2a5f17c2a2232506feb9d6
## What changed
Read rollout evidence from newest to oldest for both memory versions, retaining up to 8 MiB of sanitized response items and inter-agent communications, then restore chronological order. Skip malformed records and records larger than 1 MiB, and require valid session metadata in the first record within that limit.
## Testing
Add coverage for the retained byte budget, newest-record ordering, malformed and oversized records, and unsupported session metadata. Extend extraction request tests for both memory versions to verify that evidence after an oversized record reaches the model.
GitOrigin-RevId: 55ccbc2477ecb059830d3a55be12bcbc21235303
## Why
Compaction could record partial output before the response completed, leaving failed summaries in conversation history and persisted rollouts.
## What changed
Buffer compaction output until `response.completed` so failed or incomplete attempts leave no partial output in history. Record successful output before the response completion notification, preserving its compaction metadata.
## Testing
Add regression coverage for preserving messages, tool results, and token usage after a disconnected compaction stream, including after restart. Verify incomplete compaction output is excluded from subsequent requests and successful output remains observable and persisted.
GitOrigin-RevId: 8651200b2aae616000c55c1ed63283f3e2c1b8d5
## Why
Archiving or deleting a task blocked dashboard navigation until the server request finished.
## What changed
Keep the dashboard interactive for browsing while archive and delete requests are pending. Hide the affected task immediately and show an inline progress message. Allow selection movement and search while preventing task switching, new tasks, and leaving the dashboard until the request completes.
Preserve the dashboard selection when removing the current task detaches the session.
## Testing
Update archive and delete progress tests and snapshots to cover navigation, resize handling, immediate task hiding, and suppression of task switching and creation while requests are pending.
GitOrigin-RevId: ff6555602bcd84d38e00de55c3032f442589fdcb
## Why
Daemon package tests copy full debug CLI packages. Running these I/O-heavy cases alongside other tests can increase shared-disk writeback pressure.
## What changed
- Move package installation and replacement coverage into the `app_server_daemon_package` test binary, sharing daemon fixtures with the lifecycle tests.
- Reserve all nextest test threads for each package test and add an exclusive Bazel target that runs the cases serially on Linux and macOS.
- Hard-link the prepared fixture executable during package setup, while retaining real independent package copies in the installer.
GitOrigin-RevId: 255ac8caf75d9eb61bafe68f1f9bcfa99ee72484
## Why
Persisted subagent threads could be reported as unavailable when selected after unloading, even though their saved history could be restored.
## What changed
Attempt to resume selected threads marked closed, including those with a cached live channel, and restore their transcript through the existing attachment flow.
## Testing
Extend coverage for V1 and V2 subagents to verify saved transcript restoration, the appropriate direct-input behavior, and reattachment when a close notification from the previous runtime is still queued.
GitOrigin-RevId: f45d16b954ce5f9f30ca4c6c6f640937390dd78d
## Why
Standalone thread settings updates cleared the running turn's continuation lineage, preventing recovery after a daemon restart.
## What changed
Preserve continuation lineage while a task is registered. Continue invalidating pending continuations for idle, reserved, and finishing turns, and record started-turn lineage atomically with task registration.
## Testing
Extend settings invalidation coverage to idle, reserved, and finishing turns. Exercise an in-flight reasoning effort update before compaction, then verify cold resume preserves the turn's frozen settings and allows continuation. Wait for thread idle before testing idle continuation.
GitOrigin-RevId: d7c316af6a4c871790bb57f0af9892bb30871ac8
## Why
Incremental-tool windows recorded base instructions only at setup, so a catalog refresh for the same model could leave active instructions stale. Instruction changes need to reach the model without rewriting the existing history prefix.
## What changed
- Track model identity and instruction content independently, appending a `model_instructions` developer message when either changes. Explicitly mark replacement or removal of base instructions, and avoid repeating unchanged updates.
- Start new windows after compaction with the latest model instructions while preserving custom base instructions.
- Preserve the recorded window base during local compaction retries, including empty instructions, and rebuild current model instructions when reconstructing child context.
## Testing
Add integration tests and request snapshots for catalog refreshes, instruction removal, model switches, compaction, restart, and forks. Extend regression coverage for legacy snapshots and local compaction retries.
GitOrigin-RevId: eeca69067b4d9cd91c817732d79b4d5c1faa18b9
Alex Kira